© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53127
    Prev
    Next
    INDEX
    Explanations

    html tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_31_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🍁
    0.35
    如果你
    0.32
    古
    0.32
     mendatang
    0.32
    橛
    0.32
    Dear
    0.32
     কাহ
    0.31
    啪
    0.31
    راه
    0.31
    overview
    0.31
    POSITIVE LOGITS
     transitory
    0.37
    primarily
    0.37
    aminated
    0.35
    ρυθ
    0.34
    աստ
    0.34
     OCE
    0.33
     insolvent
    0.33
     primarily
    0.33
    oxine
    0.33
     cups
    0.32
    Activations Density 0.002%

    No Known Activations